exa-search

Warn

Audited by Snyk on May 30, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via Exa’s runtime web retrieval: scripts/exa_search.py calls client.search_and_contents(...) with --text/--highlights, and the returned results[].text / results[].highlights (scraped from public web pages by Exa) are then emitted for downstream LLM use.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 30, 2026, 03:59 AM
Issues
1
Security Audit — snyk — exa-search